Thursday, February 17th 2011
NVIDIA Readying GeForce GTX 550 Ti for March
NVIDIA is reportedly working on a new mainstream GPU for a mid-March launch. The graphics giant is planning to name it GeForce GTX 550 Ti, that's right, "GTX" prefix and "Ti" suffix monikers being extended to the core mainstream, in place of the typical "GTS". The new GPU will be based on the 40 nanometer GF116 silicon. Its exact specifications are not known, except that the GPU will use a 128-bit wide GDDR5 memory interface, and will be pin-compatible with GF106, on which is based the GeForce GTS 450. Its performance is estimated to be up to 35% higher than ATI Radeon HD 5770. Due to an electrical redesign over GF106, the GTX 550 Ti is expected to have a TDP of just 110W, nearly the same as that of the GTS 450, except having higher performance. The NVIDIA GeForce GTX 550 Ti is slated for release on 15 March, 2011.
Source:
VR-Zone
50 Comments on NVIDIA Readying GeForce GTX 550 Ti for March
I do hope NV will launch this product at reasonable price. If it match the GTX 460 it'll be Awesome..till then waiting for a review:)
This card sounds like a updated 450 thats all.
HOld up , it is to be on the same level as a 460?
Guess i will be buying this card , its suppose to have 1 6 pin right?
P.S glad to see you using cards with Power Adaptors :D you have come along way from PCI cards lol.
And i think about the bandwidth like this
Low end cards = 128 bit
Mid = 256
High = 320 or more
Now, I'm always of the kind that thinks that bandwidth is not as important and thus I think that 128 bit for this kind of card is a good compromise, but it's going to be a limiting factor anyways. It all comes down to the fact that we (enthusiasts) tend to see mid-range cards as "just good enough" cards, and as such "good enough" specs are due, especially bandwidth. People who usually buy mid-range think differently though: they want the best they can get and want to see as few corners cut as posible. Of course avoiding cutting corners is far more difficult on lower segments if you want to keep them cheap, but... it's human nature to want more!
So while I don't completely agree with their logic, I can't refute it either. That's the bottom line of this long (and probably worthless) post.
At any rate, I'm not saying the card should have more ROP/bandwidth, in fact I am a huge supporter of increasing SP to ROP ratio in most of Nvidia cards*. But at the same time I can only say that such a card (128 bit, 256 SP) would definately benefit from a wider bus. Is that economical or does even make any sense? Probably not. Most definately not, but that does not change the fact that for some scenarios and some people it would make more sense, and there's nothing wrong in them asking for what they want, asking is free after all.
*I even made a chart comparing all the specs of every Fermi card in percentages and comparing them to actual performance from Wizz's reviews and it turns out that for most of the Fermi cards released to date the SP power is linearly proportional to the obtained performance with a variation of +/- 2%. The exception is the GTX560 which performs some 5% lower than what I "predicted", and that suggests a small memory/rop limitation.
EDIT: btw is there something wrong with me or are the 2 charts in your last post identical?
That is good news and i don't want to say that GTX460 is going to be priced even lower :D
So, you might want to have your PSU loaded at 50% for many reasons (reliability, noise, heat...) but efficiency really shouldn't be your reason, you will never recover the extra $$ you paid for the higher wattage PSU. Never.